chaiml-rirv938-0sw-96p_18713

developer_uid: NischayDnk

submission_id: chaiml-rirv938-0sw-96p_18713_v12

model_name: chaiml-rirv938-0sw-96p_18713_v12

model_group: ChaiML/rirv938-0sw-96p-4

status: torndown

timestamp: 2025-09-09T20:19:32+00:00

num_battles: 6305

num_wins: 3394

celo_rating: 1288.39

family_friendly_score: 0.4878

family_friendly_standard_error: 0.007068962583010325

submission_type: basic

model_repo: ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 7

max_input_tokens: 1400

max_output_tokens: 70

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.7025053602998002, 'latency_mean': 1.4233812952041627, 'latency_p50': 1.4245991706848145, 'latency_p90': 1.5647512435913087}, {'batch_size': 4, 'throughput': 1.711260156571077, 'latency_mean': 2.3305458998680115, 'latency_p50': 2.3149737119674683, 'latency_p90': 2.5588826179504394}, {'batch_size': 5, 'throughput': 1.8913471626229068, 'latency_mean': 2.6212861692905425, 'latency_p50': 2.6188955307006836, 'latency_p90': 2.9542765617370605}, {'batch_size': 8, 'throughput': 2.217890504712064, 'latency_mean': 3.570421030521393, 'latency_p50': 3.591084361076355, 'latency_p90': 3.980194330215454}, {'batch_size': 10, 'throughput': 2.3794917878309785, 'latency_mean': 4.162217547893524, 'latency_p50': 4.142740726470947, 'latency_p90': 4.710123467445373}, {'batch_size': 12, 'throughput': 2.4474015653452983, 'latency_mean': 4.847371948957443, 'latency_p50': 4.870166063308716, 'latency_p90': 5.442914390563965}, {'batch_size': 15, 'throughput': 2.5419172469063143, 'latency_mean': 5.837640085220337, 'latency_p50': 5.873888731002808, 'latency_p90': 6.534965896606445}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: chaiml-rirv938-0sw-96p_18713_v12

ineligible_reason: max_output_tokens!=64

is_internal_developer: False

language_model: ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0

model_size: 13B

ranking_group: single

throughput_3p7s: 2.28

us_pacific_date: 2025-09-09

win_ratio: 0.5383029341792228

generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', '####', '\n', '<|im_end|>', '</s>', '<|im_start|>', '<|eot_id|>', 'You:', 'Bot:'], 'max_input_tokens': 1400, 'best_of': 7, 'max_output_tokens': 70}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-rirv938-0sw-96p-18713-v12-mkmlizer
Waiting for job on chaiml-rirv938-0sw-96p-18713-v12-mkmlizer to finish
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║  belonging to:                                                      ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ║                                                                     ║
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: Downloaded to shared memory in 15.480s
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: Checking if ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0 already exists in ChaiML
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpoxn89wr9, device:0
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: quantized model in 28.008s
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: Processed model ChaiML/rirv938-0sw-96p-4ff-cha_93234_v2_w0 in 43.489s
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: creating bucket guanaco-mkml-models
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v12/nvidia
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v12/nvidia/config.json
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v12/nvidia/special_tokens_map.json
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v12/nvidia/tokenizer_config.json
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v12/nvidia/tokenizer.json
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-rirv938-0sw-96p-18713-v12/nvidia/flywheel_model.0.safetensors
chaiml-rirv938-0sw-96p-18713-v12-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:07<23:59,  3.99s/it]
Loading 0:   2%|▏         | 6/363 [00:08<06:19,  1.06s/it]
Loading 0:   4%|▍         | 14/363 [00:08<02:02,  2.85it/s]
Loading 0:   6%|▌         | 20/363 [00:08<01:12,  4.72it/s]
Loading 0:   7%|▋         | 25/363 [00:08<00:50,  6.73it/s]
Loading 0:   9%|▉         | 32/363 [00:08<00:31, 10.53it/s]
Loading 0:  10%|█         | 38/363 [00:08<00:22, 14.21it/s]
Loading 0:  12%|█▏        | 44/363 [00:08<00:17, 18.60it/s]
Loading 0:  14%|█▍        | 51/363 [00:08<00:13, 23.20it/s]
Loading 0:  16%|█▋        | 59/363 [00:09<00:09, 30.84it/s]
Loading 0:  18%|█▊        | 65/363 [00:09<00:08, 33.78it/s]
Loading 0:  20%|█▉        | 71/363 [00:09<00:07, 37.70it/s]
Loading 0:  21%|██        | 77/363 [00:09<00:06, 42.18it/s]
Loading 0:  23%|██▎       | 83/363 [00:09<00:06, 43.38it/s]
Loading 0:  25%|██▍       | 89/363 [00:09<00:06, 45.45it/s]
Loading 0:  26%|██▋       | 96/363 [00:09<00:06, 44.30it/s]
Loading 0:  29%|██▊       | 104/363 [00:09<00:04, 52.40it/s]
Loading 0:  30%|███       | 110/363 [00:10<00:04, 51.23it/s]
Loading 0:  32%|███▏      | 116/363 [00:10<00:04, 51.40it/s]
Loading 0:  34%|███▍      | 123/363 [00:10<00:04, 48.44it/s]
Loading 0:  36%|███▌      | 131/363 [00:10<00:04, 54.59it/s]
Loading 0:  38%|███▊      | 137/363 [00:10<00:07, 31.70it/s]
Loading 0:  39%|███▉      | 142/363 [00:10<00:06, 34.66it/s]
Loading 0:  41%|████▏     | 150/363 [00:11<00:05, 38.79it/s]
Loading 0:  44%|████▍     | 159/363 [00:11<00:04, 43.79it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:04, 47.36it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:03, 53.80it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:03, 52.87it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:03, 54.08it/s]
Loading 0:  54%|█████▎    | 195/363 [00:11<00:03, 51.68it/s]
Loading 0:  56%|█████▌    | 203/363 [00:12<00:02, 58.42it/s]
Loading 0:  58%|█████▊    | 210/363 [00:12<00:02, 58.18it/s]
Loading 0:  60%|█████▉    | 217/363 [00:12<00:02, 58.59it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:02, 54.57it/s]
Loading 0:  64%|██████▎   | 231/363 [00:12<00:02, 51.47it/s]
Loading 0:  66%|██████▌   | 239/363 [00:12<00:02, 58.14it/s]
Loading 0:  68%|██████▊   | 246/363 [00:12<00:02, 57.94it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:01, 56.85it/s]
Loading 0:  71%|███████   | 258/363 [00:13<00:02, 51.50it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:01, 58.55it/s]
Loading 0:  75%|███████▌  | 273/363 [00:13<00:01, 58.50it/s]
Loading 0:  77%|███████▋  | 280/363 [00:13<00:01, 57.97it/s]
Loading 0:  79%|███████▉  | 286/363 [00:13<00:01, 51.28it/s]
Loading 0:  81%|████████  | 294/363 [00:13<00:01, 50.99it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 57.75it/s]
Loading 0:  85%|████████▌ | 309/363 [00:13<00:00, 56.44it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:01, 34.26it/s]
Loading 0:  88%|████████▊ | 321/363 [00:14<00:01, 35.89it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 40.98it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:00, 45.27it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 52.11it/s]
Loading 0:  97%|█████████▋| 353/363 [00:15<00:00, 51.39it/s]
Loading 0:  99%|█████████▉| 359/363 [00:15<00:00, 51.24it/s]
                                                            
Job chaiml-rirv938-0sw-96p-18713-v12-mkmlizer completed after 73.95s with status: succeeded
Stopping job with name chaiml-rirv938-0sw-96p-18713-v12-mkmlizer
Pipeline stage MKMLizer completed in 74.41s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.42s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-rirv938-0sw-96p-18713-v12
Waiting for inference service chaiml-rirv938-0sw-96p-18713-v12 to be ready
Failed to get response for submission chaiml-cogito32b-dpos2_39363_v15: ('http://guanaco-model-mesh-load-balancer.model-mesh.k2.chaiverse.com/models/chaiml-cogito32b-dpos2_39363_v15/predict', '{"detail":"1 validation error for RuntimeResponse\\npredictions\\n  Field required [type=missing, input_value={\'detail\': \\"503, message=...os2_39363_v15/predict\'\\"}, input_type=dict]\\n    For further information visit https://errors.pydantic.dev/2.11/v/missing"}')
Inference service chaiml-rirv938-0sw-96p-18713-v12 ready after 100.67018747329712s
Pipeline stage MKMLDeployer completed in 101.09s
run pipeline stage %s
Running pipeline stage StressChecker
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 1.7334823608398438s
Received healthy response to inference request in 2.0739426612854004s
Received healthy response to inference request in 1.5266938209533691s
Received healthy response to inference request in 1.402414321899414s
5 requests
1 failed requests
5th percentile: 1.4272702217102051
10th percentile: 1.4521261215209962
20th percentile: 1.501837921142578
30th percentile: 1.568051528930664
40th percentile: 1.650766944885254
50th percentile: 1.7334823608398438
60th percentile: 1.8696664810180663
70th percentile: 2.005850601196289
80th percentile: 5.681966972351077
90th percentile: 12.898015594482423
95th percentile: 16.506039905548093
99th percentile: 19.392459354400636
mean time: 5.37011947631836
%s, retrying in %s seconds...
Received healthy response to inference request in 1.4916727542877197s
Received healthy response to inference request in 1.7011692523956299s
Received healthy response to inference request in 1.7057831287384033s
Received healthy response to inference request in 1.3240647315979004s
Received healthy response to inference request in 1.3867590427398682s
5 requests
0 failed requests
5th percentile: 1.336603593826294
10th percentile: 1.3491424560546874
20th percentile: 1.3742201805114747
30th percentile: 1.4077417850494385
40th percentile: 1.449707269668579
50th percentile: 1.4916727542877197
60th percentile: 1.5754713535308837
70th percentile: 1.6592699527740478
80th percentile: 1.7020920276641847
90th percentile: 1.703937578201294
95th percentile: 1.7048603534698485
99th percentile: 1.7055985736846924
mean time: 1.5218897819519044
Pipeline stage StressChecker completed in 36.74s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.64s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.76s
Shutdown handler de-registered
chaiml-rirv938-0sw-96p_18713_v12 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-rirv938-0sw-96p-18713-v12-profiler
Waiting for inference service chaiml-rirv938-0sw-96p-18713-v12-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2376.43s
Shutdown handler de-registered
chaiml-rirv938-0sw-96p_18713_v12 status is now inactive due to auto deactivation removed underperforming models
chaiml-rirv938-0sw-96p_18713_v12 status is now torndown due to DeploymentManager action